Chapter 6 - Normal Distribution

Chapter Overview

This chapter covers concepts related to the normal distribution, including continuous random variables, probability density curves, and the Central Limit Theorem. These foundational principles are crucial for statistical analysis within the context of MATH 220.

Continuous Random Variables

  • Definition: A random variable represents numerical outcomes of experiments; continuous random variables can take any value within a specified interval (e.g., particulate emissions for vehicles).

  • As sample sizes increase, data representation becomes smoother (narrower rectangles in histograms can approximate continuous curves).

Probability Density Curves

  • Used to describe continuous random variables.

  • The area under the curve equals 1, representing the total probability. The area between two values indicates the proportion of the population within that interval.

  • Probability of a specific value is 0 because a single point has no width. Hence, P(a < X < b) is equivalent to P(a ≤ X ≤ b).

The Normal Distribution

  • Characteristics: Normal curves are symmetric about their mean, which also serves as the mode. Their shape depends on the population’s mean and standard deviation.

  • Key Properties:

    • Approximately 68% of the data falls within one standard deviation of the mean.

    • About 95% falls within two standard deviations, and about 99.7% within three (the Empirical Rule).

Z-Scores

  • A z-score standardizes values to allow comparisons across different distributions using the formula: 𝑧 = (𝑥 − μ) / σ.

  • Positive z-scores indicate values above the mean, while negative scores indicate values below. Examples show how to calculate and interpret z-scores for individual heights versus mean values.

Sampling Distribution of the Sample Mean

  • Summary statistics like the sample mean (𝑥̅) are derived from random samples. The distribution of these means will approximate a normal distribution as sample sizes increase due to the Central Limit Theorem.

  • For populations with any distribution, larger sample sizes (n > 30) yield a sampling distribution that is approximately normal, with mean 𝝁𝑥̅ = μ and standard deviation 𝝈𝑥̅ = σ / √n.

The Central Limit Theorem for Proportions

  • The sample proportion (𝑝̂ = x/n) forms its own distribution, with mean 𝝁𝑝̂ = p and standard deviation 𝝈𝑝̂ = √(p(1−p)/n).

  • Conditions for normal approximation include ensuring both np and n(1-p) are greater than 10.

Assessing Normality

  • Various graphical methods (dot plots, boxplots, histograms, etc.) help assess whether a sample can be treated as drawn from a normal distribution.

  • Specific features that indicate nonnormality include outliers, skewness, and multimodality.

In-Class Problems

  • A series of in-class problems is provided to apply concepts like z-scores, normal probabilities, and the behaviors of sample means to reinforce understanding of the material covered in Chapter 6.